Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.12358/24781
Title | Inverse weighted clustering algorithm |
---|---|
Untitled | |
Abstract |
We discuss a new form of clustering which overcomes some of the problems of traditional K-means such as sensitivity to initial conditions. We illustrate convergence of the algorithm on a number of artificial data sets. We then introduce a variant of this clustering which preserves some aspects of global topology in the organisation of the centres. We illustrate on artificial data before using it to visualise some standard datasets. |
Authors | |
Type | Journal Article |
Date | 2007 |
Published in | Computing and Information Systems |
Series | Volume: 11, Number: 2 |
Publisher | UNIVERSITY OF PAISLEY |
Citation | |
Item link | Item Link |
License | ![]() |
Collections | |
Files in this item | ||
---|---|---|
Ashour, Wesam M._25.pdf | 275.8Kb |